Dian Chen

12

Papers

68

Total Citations

Papers (12)

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Learning to Drive via Asymmetric Self-Play

Multi-Frame Self-Supervised Depth With Transformers

Contrastive Test-Time Adaptation

Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles

Viewpoint Equivariance for Multi-View 3D Object Detection

Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking

Learning To Drive From a World on Rails

Towards Zero-Shot Scale-Aware Monocular Depth Estimation

Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion

MotionLM: Multi-Agent Motion Forecasting as Language Modeling

Learning From All Vehicles